📖About

When a step-creation initiative exists for an initiative, the original must stay blocked until the step-creation completes. The step-creation close-hook then retriggers the original. Otherwise both run in parallel and the step-creation is wasted. Fix: (1) prevent unblocking an initiative when an open step-creation exists. (2) step-creation close-hook checks if original is already executing and skips retrigger.

⚖️Decisions

• Elrond's bypass methodology checklist (a reminder, not a gate -- you've got this): 0. File it requested_mode='bypass' (planner-vs-bypass is a deliberate choice). bypass_start REFUSES a non-bypass initiative (CAROL-INI-1846), and the dispatcher only skips the bypass lane when the mode says bypass -- a 'planner' mistag lets Merlin's pipeline grab the placeholder step and block your finished work. 1. Filed as planned status -- let the bypass claim/activate it; never file active. 2. Open the bypass (bypass_start) with your droid id + the remediation answer (remediates_initiative_id=NNN, or remediates_nothing=True). 3. Work the blocks for your work-type: template -> design -> code -> test -> review. Do the real work; record decisions on the initiative as you make them. 4. Reality is recorded for you at close -- code (files changed), each decision, and the twin-review verdict become real activities tied to this initiative and show in the Activity Tracker like a planner run (CAROL-INI-1840). No dummy rows. 5. Keep the initiative status moving; it parks in 'reviewing' and is tagged uat-pending for you at close (CAROL-INI-1836), so the stuck-watchdog leaves it alone until UAT. 6. Close runs the gates (design/architecture compliance + caller-audit). If a gate flags something pre-existing or unrelated to your change, waive it with a clear written rationale -- audit, don't skip. 7. Bypass skips the planner's auto-orchestration, NOT the standards. Same template checklist, same review, same observability as a planner run. (elrond)
• [status-router] planned -> reviewing | event=operator_put | PUT /api/initiatives (operator)
• [status-router] reviewing -> blocked | event=stuck_10min_no_activity | Elrond safety net: initiative has had no activity for 10+ minutes. Blocking under the parallel safety mechanism. (el-watchdog)
• Elrond blocked initiative under the CAROL-INI-2162 dead-Albus protocol. Albus was supposed to wake for step 0 (cause=albus_no_show) but did not respond. Cause: albus_no_show. Reason: Elrond safety net: initiative stranded 10+ min. Albus wake failed or produced no useful result. (el-s1)
• RSI diagnosed: 2026-07-01 07:16:28 -> improvement #(none). ({'_raw': "ROOT CAUSE: A dead-Albus protocol caused the initiative to stall with no activity for 10 minutes, triggering Elrond's parallel safety net and blocking the initiative. \nIMPROVEMENT: Enforce a dependency lock to ensure step creation and original initiative execution are strictly sequentia (el-rsi-eng-01)
• Orion remediated: Albus RSI group diagnosis (via INI 1000168): [procedural, confidence high] The initiative blocked because Albus (the assigned executor) never received or processed the wake-up signal at step 0. The initiative was set to 'executing' by the review inferer at 2026-07-01 04:18:18, but no execution agent (Albus) was triggered. The Elrond safety net then blocked it after 10+ minutes of inactivity. This is a procedural failure: the execution pipeline expected an automated start from Albus, but Albus was not available or the wake mechanism failed. (orion)
• Orion remediated: Albus RSI group diagnosis (via INI 999900395): [procedural, confidence high] The initiative was filed as bypass mode but never received a bypass_start activation: the executor Albus never claimed step 0 (albus_no_show), leaving the initiative idle in 'reviewing' status until Elrond's safety net blocked it after 10+ minutes. Examination of the initiatives DB shows no dispatch_queue entry for this initiative, and /tmp/carol_claude_concurrency.log shows no lock acquisitions for Albus around the relevant time, confirming the procedural failure was a missing trigger rather than a work or (orion)
• Orion remediated: Albus RSI group diagnosis (via INI 1000166): [procedural, confidence high] The initiative was repeatedly retracted from the 3-deep dispatch queue because it could not stay in the top-3 priority window long enough for an operator push, resulting in no execution and a 10-minute inactivity timeout that triggered the Elrond safety net. (orion)
• Orion remediated: Albus RSI group diagnosis (via INI 999900406): [procedural, confidence high] The initiative blocked because it was set to 'reviewing' by an operator at 2026-06-30 03:57:49, but no executor (Albus or operator) ever performed the code changes described in the initiative; the Elrond safety net triggered after 10+ minutes of inactivity, and subsequent attempts to diagnose the block reused Albus-dependent processes that themselves failed to execute, creating a self-reinforcing procedural deadlock. (orion)
• [rsi-group] cause=stuck_10min_no_activity members=[999900413, 999900370, 999900481, 999900486, 999900328, 999900432, 999900502, 999900522, 999900647, 999900506, 999900516, 999900542, 999900572, 999900575, 999900577, 999900591, 999900593, 999900607, 999900608, 999900613, 999900625] (leverage-first pick: largest same-cause group, 21 members) (elrond.rsi_loop)
• [status-router] blocked -> diagnosis | event=diagnosis_start | RSI loop: leverage pick cause=stuck_10min_no_activity group_size=21 (blocked since 2026-07-01 06:52:55); Albus diagnosis INI 999900698 (el-rsi-loop-01)
• Orion remediation in progress: INI-999900698 bypass opened — CAROL-INI-696: an Orion-driven bypass has been opened to remediate this parent. The canonical Orion remediated: marker will be posted on close — see cookbook 156 / 155. (shared.bypass.bypass_start)
• Albus RSI diagnosis (root cause): [procedural, confidence high] The initiative was filed as 'bypass' mode but was erroneously set to 'reviewing' status by an operator PUT instead of being opened via bypass_start, causing the execution pipeline to never trigger Albus; it remained idle until Elrond's 10-minute inactivity safety net blocked it. This is a recurring procedural pattern where bypass initiatives are mishandled, as confirmed by the empty execution history and the lack of any dispatch queue entry. (albus)
• Albus RSI recommendations: - Re-file the initiative as 'planned' status, then immediately execute bypass_start with remediates_initiative_id=999900413 to properly open the bypass lane and trigger Albus. - Ensure no operator puts bypass mode initiatives to 'reviewing' directly; enforce that bypass_start is the only entry point for execution. - Consider adding a validation gate in the status-router to reject direct 'reviewing' transitions for bypass-mode initiatives. || Next attempt succeeds because: If bypass_start is used correctly, Albus will be triggered, execute the work, and the initiative will progress normally. The fix itself (enforcing dependency lock) is sound; the only failure was the procedural gate mismatch. (albus)
• Orion remediated: INI-999900698 bypass closed — CAROL-INI-696 close-marker: the Orion bypass INI-999900698 filed against this parent reached terminal state (closed). This row's literal prefix Orion remediated: is the canonical signal the cookbook-155 dispatcher gate looks for. (shared.bypass.bypass_end)
• [rsi-group-member-done] 999900370 -> retriggered as 999900703 (elrond.rsi_loop)
• [rsi-group-member-failed] 999900481 error: BrokenPipeError(32, 'Broken pipe') (elrond.rsi_loop)
• [rsi-group-member-failed] 999900486 error: BrokenPipeError(32, 'Broken pipe') (elrond.rsi_loop)
• [rsi-group-member-failed] 999900328 error: BrokenPipeError(32, 'Broken pipe') (elrond.rsi_loop)
• [rsi-group-member-failed] 999900432 error: BrokenPipeError(32, 'Broken pipe') (elrond.rsi_loop)
• [rsi-group-member-failed] 999900502 retrigger refused: {'ok': False, 'reason': 'create_returned_no_id: {\'error\': \'INI2205_BAD_CRITERIA: All success criteria appear process-only (LLM confirmed). Each must describe a measurable user-visible outcome. FAIL\', \'criteria\': ["The original initiative carrie (elrond.rsi_loop)
• [rsi-group-member-failed] 999900522 retrigger refused: {'ok': False, 'reason': 'create_returned_no_id: {\'error\': \'INI2205_BAD_CRITERIA: All success criteria appear process-only (LLM confirmed). Each must describe a measurable user-visible outcome. FAIL\', \'criteria\': [\'Every actionable audit findin (elrond.rsi_loop)
• [rsi-group-member-failed] 999900647 retrigger refused: {'ok': False, 'reason': 'create_returned_no_id: {\'error\': \'INI2205_BAD_CRITERIA: All success criteria appear process-only (LLM confirmed). Each must describe a measurable user-visible outcome. FAIL\', \'criteria\': ["The original initiative carrie (elrond.rsi_loop)
• [rsi-group-member-done] 999900506 -> retriggered as 999900709 (elrond.rsi_loop)
• [rsi-group-member-failed] 999900516 error: BrokenPipeError(32, 'Broken pipe') (elrond.rsi_loop)
• [rsi-group-member-failed] 999900542 retrigger refused: {'ok': False, 'reason': 'create_returned_no_id: {\'error\': \'INI2205_BAD_CRITERIA: All success criteria appear process-only (LLM confirmed). Each must describe a measurable user-visible outcome. FAIL\', \'criteria\': [\'al_watch_01.py is deleted (or (elrond.rsi_loop)
• [rsi-group-member-failed] 999900572 retrigger refused: {'ok': False, 'reason': 'create_returned_no_id: {\'error\': \'INI2205_BAD_CRITERIA: All success criteria appear process-only (LLM confirmed). Each must describe a measurable user-visible outcome. FAIL\', \'criteria\': [\'When Albus is unreachable, El (elrond.rsi_loop)
• [rsi-group-member-failed] 999900575 retrigger refused: {'ok': False, 'reason': 'create_returned_no_id: {\'error\': \'INI2205_BAD_CRITERIA: All success criteria appear process-only (LLM confirmed). Each must describe a measurable user-visible outcome. FAIL\', \'criteria\': [\'All cross-build Carol initiat (elrond.rsi_loop)
• [rsi-group-member-done] 999900577 -> retriggered as 999900730 (elrond.rsi_loop)
• [rsi-group-member-failed] 999900591 error: BrokenPipeError(32, 'Broken pipe') (elrond.rsi_loop)
• [rsi-group-member-failed] 999900593 retrigger refused: {'ok': False, 'reason': 'create_returned_no_id: {\'error\': \'INI2205_BAD_CRITERIA: All success criteria appear process-only (LLM confirmed). Each must describe a measurable user-visible outcome. FAIL\', \'criteria\': [\'INI-0015 closed (properly del (elrond.rsi_loop)
• [rsi-group-member-failed] 999900607 retrigger refused: {'ok': False, 'reason': 'create_returned_no_id: {\'error\': \'INI2205_BAD_CRITERIA: All success criteria appear process-only (LLM confirmed). Each must describe a measurable user-visible outcome. FAIL\', \'criteria\': ["grep -r \'frankfurt\' across n (elrond.rsi_loop)
• [rsi-group-member-failed] 999900608 retrigger refused: {'ok': False, 'reason': 'create_returned_no_id: {\'error\': \'INI2205_BAD_CRITERIA: All success criteria appear process-only (LLM confirmed). Each must describe a measurable user-visible outcome. FAIL\', \'criteria\': ["The original initiative carrie (elrond.rsi_loop)
• [rsi-group-member-failed] 999900613 error: BrokenPipeError(32, 'Broken pipe') (elrond.rsi_loop)
• [rsi-group-member-failed] 999900625 error: BrokenPipeError(32, 'Broken pipe') (elrond.rsi_loop)
• Orion remediated: Albus RSI diagnosis: [procedural, confidence high] The initiative was filed as 'bypass' mode but was erroneously set to 'reviewing' status by an operator PUT instead of being opened via bypass_start, causing the execution pipeline to never trigger Albus; it remained idle until Elrond's 10-minute inactivity safety net blocked it. This is a recurring procedural pattern where bypass initiatives are mishandled, as confirmed by the empty execution history and the lack of any dispatch queue entry. (orion)
• [rsi-retrigger-failed] {'ok': False, 'reason': 'create_returned_no_id: {\'error\': \'INI2205_BAD_CRITERIA: All success criteria appear process-only (LLM confirmed). Each must describe a measurable user-visible outcome. FAIL\', \'criteria\': [\'Step-creation close-hook checks if parent is already executing before retriggering\', \'Cookbook entry #381 documenting sequential constraint\'], \'suggestion\': "Success criteria (elrond.rsi_loop)
• Orion remediated: Albus RSI diagnosis: [procedural, confidence high] The initiative was filed as 'bypass' mode but was erroneously set to 'reviewing' status by an operator PUT instead of being opened via bypass_start, causing the execution pipeline to never trigger Albus; it remained idle until Elrond's 10-minute inactivity safety net blocked it. This is a recurring procedural pattern where bypass initiatives are mishandled, as confirmed by the empty execution history and the lack of any dispatch queue entry. (orion)
• [rsi-retrigger-failed] {'ok': False, 'reason': 'create_returned_no_id: {\'error\': \'INI2205_BAD_CRITERIA: All success criteria appear process-only (LLM confirmed). Each must describe a measurable user-visible outcome. FAIL\', \'criteria\': [\'Step-creation close-hook checks if parent is already executing before retriggering\', \'Cookbook entry documenting sequential constraint\'], \'suggestion\': "Success criteria must (elrond.rsi_loop)
• Orion remediated: Albus RSI diagnosis: [procedural, confidence high] The initiative was filed as 'bypass' mode but was erroneously set to 'reviewing' status by an operator PUT instead of being opened via bypass_start, causing the execution pipeline to never trigger Albus; it remained idle until Elrond's 10-minute inactivity safety net blocked it. This is a recurring procedural pattern where bypass initiatives are mishandled, as confirmed by the empty execution history and the lack of any dispatch queue entry. (orion)
• [rsi-retrigger-failed] {'ok': False, 'reason': 'create_returned_no_id: {\'error\': \'INI2205_BAD_CRITERIA: All success criteria appear process-only (LLM confirmed). Each must describe a measurable user-visible outcome. FAIL\', \'criteria\': [\'Step-creation close-hook checks if parent is already executing before retriggering\', \'Cookbook entry #381 documenting sequential constraint\'], \'suggestion\': "Success criteria (elrond.rsi_loop)
• [rsi-retrigger-stuck] OPERATOR ACTION NEEDED: 3 consecutive retrigger filing failures; the RSI loop skips this family until the rsi-retrigger-stuck tag is removed. Last error: {'ok': False, 'reason': 'create_returned_no_id: {\'error\': \'INI2205_BAD_CRITERIA: All success criteria appear process-only (LLM confirmed). Each must describe a measurable user-visible outcome. FAIL\', \'criteria\': [\'Step-creation close-hook checks if parent is already executing before retrigger (elrond.rsi_loop)
• Orion remediated: Albus RSI diagnosis: [procedural, confidence high] The initiative was filed as 'bypass' mode but was erroneously set to 'reviewing' status by an operator PUT instead of being opened via bypass_start, causing the execution pipeline to never trigger Albus; it remained idle until Elrond's 10-minute inactivity safety net blocked it. This is a recurring procedural pattern where bypass initiatives are mishandled, as confirmed by the empty execution history and the lack of any dispatch queue entry. (orion)
• [rsi-retrigger-failed] {'ok': False, 'reason': 'create_returned_no_id: {\'error\': \'INI2205_BAD_CRITERIA: All success criteria appear process-only (LLM confirmed). Each must describe a measurable user-visible outcome. FAIL\', \'criteria\': [\'Step-creation close-hook checks if parent is already executing before retriggering\', \'Cookbook entry #381 documenting sequential constraint\'], \'suggestion\': "Success criteria (elrond.rsi_loop)
• [rsi-retrigger-stuck] OPERATOR ACTION NEEDED: 4 consecutive retrigger filing failures; the RSI loop skips this family until the rsi-retrigger-stuck tag is removed. Last error: {'ok': False, 'reason': 'create_returned_no_id: {\'error\': \'INI2205_BAD_CRITERIA: All success criteria appear process-only (LLM confirmed). Each must describe a measurable user-visible outcome. FAIL\', \'criteria\': [\'Step-creation close-hook checks if parent is already executing before retrigger (elrond.rsi_loop)
• Orion remediated: Albus RSI diagnosis: [procedural, confidence high] The initiative was filed as 'bypass' mode but was erroneously set to 'reviewing' status by an operator PUT instead of being opened via bypass_start, causing the execution pipeline to never trigger Albus; it remained idle until Elrond's 10-minute inactivity safety net blocked it. This is a recurring procedural pattern where bypass initiatives are mishandled, as confirmed by the empty execution history and the lack of any dispatch queue entry. (orion)
• [status-router] diagnosis -> closed | event=operator_put | PUT /api/initiatives (operator)
• Closed: superseded by follow-on INI 999900731 (CAROL-INI-2178-01: Step-creation and original initiative must be sequential, not parallel — enforce dependency lock) (elrond.initiative_author)

✅Success criteria

• Step-creation close-hook checks if parent is already executing before retriggering (must_have)
• Cookbook entry #381 documenting sequential constraint (must_have)